EDA and Prediction using Decision Tree Regressor

Developed by Mr.Sachin M, Data Science @IPECSolutions Pvt.Ltd, Bengaluru

import pandas as pd
Data = pd.read_csv(r'C:\Users\Dell\Documents\ipec\Datas\heart.csv')
Data.head()

C:\Users\Dell\anaconda3\Lib\site-packages\pandas\core\arrays\masked.py:60: UserWarning: Pandas requires version '1.3.6' or newer of 'bottleneck' (version '1.3.5' currently installed).
  from pandas.core import (

	age	sex	cp	trestbps	chol	fbs	restecg	thalach	exang	oldpeak	slope	ca	thal	target
0	63	1	3	145	233	1	0	150	0	2.3	0	0	1	1
1	37	1	2	130	250	0	1	187	0	3.5	0	0	2	1
2	41	0	1	130	204	0	0	172	0	1.4	2	0	2	1
3	56	1	1	120	236	0	1	178	0	0.8	2	0	2	1
4	57	0	0	120	354	0	1	163	1	0.6	2	0	2	1

Converting float data type of oldpeak to int type

Data.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 303 entries, 0 to 302
Data columns (total 14 columns):
 #   Column    Non-Null Count  Dtype  
---  ------    --------------  -----  
 0   age       303 non-null    int64  
 1   sex       303 non-null    int64  
 2   cp        303 non-null    int64  
 3   trestbps  303 non-null    int64  
 4   chol      303 non-null    int64  
 5   fbs       303 non-null    int64  
 6   restecg   303 non-null    int64  
 7   thalach   303 non-null    int64  
 8   exang     303 non-null    int64  
 9   oldpeak   303 non-null    float64
 10  slope     303 non-null    int64  
 11  ca        303 non-null    int64  
 12  thal      303 non-null    int64  
 13  target    303 non-null    int64  
dtypes: float64(1), int64(13)
memory usage: 33.3 KB

Data.oldpeak = Data.oldpeak.astype(int)
Data.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 303 entries, 0 to 302
Data columns (total 14 columns):
 #   Column    Non-Null Count  Dtype
---  ------    --------------  -----
 0   age       303 non-null    int64
 1   sex       303 non-null    int64
 2   cp        303 non-null    int64
 3   trestbps  303 non-null    int64
 4   chol      303 non-null    int64
 5   fbs       303 non-null    int64
 6   restecg   303 non-null    int64
 7   thalach   303 non-null    int64
 8   exang     303 non-null    int64
 9   oldpeak   303 non-null    int32
 10  slope     303 non-null    int64
 11  ca        303 non-null    int64
 12  thal      303 non-null    int64
 13  target    303 non-null    int64
dtypes: int32(1), int64(13)
memory usage: 32.1 KB

print(f" Number of Rows:{Data.shape[0]}\n Number of Columns:{Data.shape[1]}")

 Number of Rows:303
 Number of Columns:14

Data.columns

Index(['age', 'sex', 'cp', 'trestbps', 'chol', 'fbs', 'restecg', 'thalach',
       'exang', 'oldpeak', 'slope', 'ca', 'thal', 'target'],
      dtype='object')

Data.describe()

	age	sex	cp	trestbps	chol	fbs	restecg	thalach	exang	oldpeak	slope	ca	thal	target
count	303.000000	303.000000	303.000000	303.000000	303.000000	303.000000	303.000000	303.000000	303.000000	303.000000	303.000000	303.000000	303.000000	303.000000
mean	54.366337	0.683168	0.966997	131.623762	246.264026	0.148515	0.528053	149.646865	0.326733	0.765677	1.399340	0.729373	2.313531	0.544554
std	9.082101	0.466011	1.032052	17.538143	51.830751	0.356198	0.525860	22.905161	0.469794	1.070933	0.616226	1.022606	0.612277	0.498835
min	29.000000	0.000000	0.000000	94.000000	126.000000	0.000000	0.000000	71.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000
25%	47.500000	0.000000	0.000000	120.000000	211.000000	0.000000	0.000000	133.500000	0.000000	0.000000	1.000000	0.000000	2.000000	0.000000
50%	55.000000	1.000000	1.000000	130.000000	240.000000	0.000000	1.000000	153.000000	0.000000	0.000000	1.000000	0.000000	2.000000	1.000000
75%	61.000000	1.000000	2.000000	140.000000	274.500000	0.000000	1.000000	166.000000	1.000000	1.000000	2.000000	1.000000	3.000000	1.000000
max	77.000000	1.000000	3.000000	200.000000	564.000000	1.000000	2.000000	202.000000	1.000000	6.000000	2.000000	4.000000	3.000000	1.000000

Data.value_counts()

age  sex  cp  trestbps  chol  fbs  restecg  thalach  exang  oldpeak  slope  ca  thal  target
38   1    2   138       175   0    1        173      0      0        2      4   2     1         2
59   1    0   110       239   0    0        142      1      1        1      1   3     0         1
          2   126       218   1    1        134      0      2        1      1   1     0         1
          1   140       221   0    1        164      1      0        2      0   2     1         1
          0   170       326   0    0        140      1      3        0      0   3     0         1
                                                                                               ..
51   1    2   94        227   0    1        154      1      0        2      1   3     1         1
          0   140       299   0    1        173      1      1        2      0   3     0         1
                        298   0    1        122      1      4        1      3   3     0         1
                        261   0    0        186      1      0        2      0   2     1         1
77   1    0   125       304   0    0        162      1      0        2      3   2     0         1
Name: count, Length: 302, dtype: int64

Data['oldpeak'] = round(Data['oldpeak'])

Data.head()

	age	sex	cp	trestbps	chol	fbs	restecg	thalach	exang	oldpeak	slope	ca	thal	target
0	63	1	3	145	233	1	0	150	0	2	0	0	1	1
1	37	1	2	130	250	0	1	187	0	3	0	0	2	1
2	41	0	1	130	204	0	0	172	0	1	2	0	2	1
3	56	1	1	120	236	0	1	178	0	0	2	0	2	1
4	57	0	0	120	354	0	1	163	1	0	2	0	2	1

Data['age'].value_counts

<bound method IndexOpsMixin.value_counts of 0      63
1      37
2      41
3      56
4      57
       ..
298    57
299    45
300    68
301    57
302    57
Name: age, Length: 303, dtype: int64>

Data['sex'].value_counts

<bound method IndexOpsMixin.value_counts of 0      1
1      1
2      0
3      1
4      0
      ..
298    0
299    1
300    1
301    1
302    0
Name: sex, Length: 303, dtype: int64>

Data['cp'].value_counts

<bound method IndexOpsMixin.value_counts of 0      3
1      2
2      1
3      1
4      0
      ..
298    0
299    3
300    0
301    0
302    1
Name: cp, Length: 303, dtype: int64>

Data['trestbps'].value_counts

<bound method IndexOpsMixin.value_counts of 0      145
1      130
2      130
3      120
4      120
      ... 
298    140
299    110
300    144
301    130
302    130
Name: trestbps, Length: 303, dtype: int64>

Data['chol'].value_counts

<bound method IndexOpsMixin.value_counts of 0      233
1      250
2      204
3      236
4      354
      ... 
298    241
299    264
300    193
301    131
302    236
Name: chol, Length: 303, dtype: int64>

Data['fbs'].value_counts

<bound method IndexOpsMixin.value_counts of 0      1
1      0
2      0
3      0
4      0
      ..
298    0
299    0
300    1
301    0
302    0
Name: fbs, Length: 303, dtype: int64>

Data['restecg'].value_counts

<bound method IndexOpsMixin.value_counts of 0      0
1      1
2      0
3      1
4      1
      ..
298    1
299    1
300    1
301    1
302    0
Name: restecg, Length: 303, dtype: int64>

Data['thalach'].value_counts

<bound method IndexOpsMixin.value_counts of 0      150
1      187
2      172
3      178
4      163
      ... 
298    123
299    132
300    141
301    115
302    174
Name: thalach, Length: 303, dtype: int64>

Data['exang'].value_counts

<bound method IndexOpsMixin.value_counts of 0      0
1      0
2      0
3      0
4      1
      ..
298    1
299    0
300    0
301    1
302    0
Name: exang, Length: 303, dtype: int64>

Data['oldpeak'].value_counts

<bound method IndexOpsMixin.value_counts of 0      2
1      3
2      1
3      0
4      0
      ..
298    0
299    1
300    3
301    1
302    0
Name: oldpeak, Length: 303, dtype: int32>

Data['slope'].value_counts

<bound method IndexOpsMixin.value_counts of 0      0
1      0
2      2
3      2
4      2
      ..
298    1
299    1
300    1
301    1
302    1
Name: slope, Length: 303, dtype: int64>

Data['ca'].value_counts

<bound method IndexOpsMixin.value_counts of 0      0
1      0
2      0
3      0
4      0
      ..
298    0
299    0
300    2
301    1
302    1
Name: ca, Length: 303, dtype: int64>

Data['thal'].value_counts

<bound method IndexOpsMixin.value_counts of 0      1
1      2
2      2
3      2
4      2
      ..
298    3
299    3
300    3
301    3
302    2
Name: thal, Length: 303, dtype: int64>

Data['target'].value_counts

<bound method IndexOpsMixin.value_counts of 0      1
1      1
2      1
3      1
4      1
      ..
298    0
299    0
300    0
301    0
302    0
Name: target, Length: 303, dtype: int64>

Data.isnull().sum()

age         0
sex         0
cp          0
trestbps    0
chol        0
fbs         0
restecg     0
thalach     0
exang       0
oldpeak     0
slope       0
ca          0
thal        0
target      0
dtype: int64

Data[Data.duplicated()]

	age	sex	cp	trestbps	chol	fbs	restecg	thalach	exang	oldpeak	slope	ca	thal	target
164	38	1	2	138	175	0	1	173	0	0	2	4	2	1

Data.drop_duplicates(inplace=True)

Data.columns

Index(['age', 'sex', 'cp', 'trestbps', 'chol', 'fbs', 'restecg', 'thalach',
       'exang', 'oldpeak', 'slope', 'ca', 'thal', 'target'],
      dtype='object')

#! pip install missingno

import missingno as msno
msno.bar(Data)

<Axes: >

print(Data.dtypes)

age         int64
sex         int64
cp          int64
trestbps    int64
chol        int64
fbs         int64
restecg     int64
thalach     int64
exang       int64
oldpeak     int32
slope       int64
ca          int64
thal        int64
target      int64
dtype: object

import matplotlib.pyplot as plt
des=Data.describe()
ax = des.plot(kind='barh')

plt.savefig('des.png',bbox_inches='tight')

transposed_Data=Data.head(10)
transposed_Data

	age	sex	cp	trestbps	chol	fbs	restecg	thalach	exang	oldpeak	slope	ca	thal	target
0	63	1	3	145	233	1	0	150	0	2	0	0	1	1
1	37	1	2	130	250	0	1	187	0	3	0	0	2	1
2	41	0	1	130	204	0	0	172	0	1	2	0	2	1
3	56	1	1	120	236	0	1	178	0	0	2	0	2	1
4	57	0	0	120	354	0	1	163	1	0	2	0	2	1
5	57	1	0	140	192	0	1	148	0	0	1	0	1	1
6	56	0	1	140	294	0	0	153	0	1	1	0	2	1
7	44	1	1	120	263	0	1	173	0	0	2	0	3	1
8	52	1	2	172	199	1	1	162	0	0	2	0	3	1
9	57	1	2	150	168	0	1	174	0	1	2	0	2	1

Data.head(10).T

	0	1	2	3	4	5	6	7	8	9
age	63	37	41	56	57	57	56	44	52	57
sex	1	1	0	1	0	1	0	1	1	1
cp	3	2	1	1	0	0	1	1	2	2
trestbps	145	130	130	120	120	140	140	120	172	150
chol	233	250	204	236	354	192	294	263	199	168
fbs	1	0	0	0	0	0	0	0	1	0
restecg	0	1	0	1	1	1	0	1	1	1
thalach	150	187	172	178	163	148	153	173	162	174
exang	0	0	0	0	1	0	0	0	0	0
oldpeak	2	3	1	0	0	0	1	0	0	1
slope	0	0	2	2	2	1	1	2	2	2
ca	0	0	0	0	0	0	0	0	0	0
thal	1	2	2	2	2	1	2	3	3	2
target	1	1	1	1	1	1	1	1	1	1

desc_Data=Data.describe().T
desc_Data

	count	mean	std	min	25%	50%	75%	max
age	302.0	54.420530	9.047970	29.0	48.00	55.5	61.00	77.0
sex	302.0	0.682119	0.466426	0.0	0.00	1.0	1.00	1.0
cp	302.0	0.963576	1.032044	0.0	0.00	1.0	2.00	3.0
trestbps	302.0	131.602649	17.563394	94.0	120.00	130.0	140.00	200.0
chol	302.0	246.500000	51.753489	126.0	211.00	240.5	274.75	564.0
fbs	302.0	0.149007	0.356686	0.0	0.00	0.0	0.00	1.0
restecg	302.0	0.526490	0.526027	0.0	0.00	1.0	1.00	2.0
thalach	302.0	149.569536	22.903527	71.0	133.25	152.5	166.00	202.0
exang	302.0	0.327815	0.470196	0.0	0.00	0.0	1.00	1.0
oldpeak	302.0	0.768212	1.071799	0.0	0.00	0.0	1.00	6.0
slope	302.0	1.397351	0.616274	0.0	1.00	1.0	2.00	2.0
ca	302.0	0.718543	1.006748	0.0	0.00	0.0	1.00	4.0
thal	302.0	2.314570	0.613026	0.0	2.00	2.0	3.00	3.0
target	302.0	0.543046	0.498970	0.0	0.00	1.0	1.00	1.0

Data.isnull().sum()

age         0
sex         0
cp          0
trestbps    0
chol        0
fbs         0
restecg     0
thalach     0
exang       0
oldpeak     0
slope       0
ca          0
thal        0
target      0
dtype: int64

import seaborn as sns
import matplotlib.pyplot as plt
import plotly.express as px

import warnings
warnings.filterwarnings('ignore')

plot_city=Data['age'].value_counts()[0:50].reset_index()
plot_city.columns=['age','Count']
px.bar(plot_city,x='age',y='Count',template='gridon',
      title='age',color='Count')

plot_city=Data['sex'].value_counts()[0:50].reset_index()
plot_city.columns=['sex','Count']
px.bar(plot_city,x='sex',y='Count',template='gridon',
      title='sex',color='Count')

plot_city=Data['cp'].value_counts()[0:50].reset_index()
plot_city.columns=['cp','Count']
px.bar(plot_city,x='cp',y='Count',template='gridon',
      title='cp',color='Count')

plot_city=Data['trestbps'].value_counts()[0:50].reset_index()
plot_city.columns=['trestbps','Count']
px.bar(plot_city,x='trestbps',y='Count',template='gridon',
      title='trestbps',color='Count')

plot_city=Data['chol'].value_counts()[0:50].reset_index()
plot_city.columns=['chol','Count']
px.bar(plot_city,x='chol',y='Count',template='gridon',
      title='chol',color='Count')

plot_city=Data['fbs'].value_counts()[0:50].reset_index()
plot_city.columns=['fbs','Count']
px.bar(plot_city,x='fbs',y='Count',template='gridon',
      title='fbs',color='Count')

plot_city=Data['restecg'].value_counts()[0:50].reset_index()
plot_city.columns=['restecg','Count']
px.bar(plot_city,x='restecg',y='Count',template='gridon',
      title='restecg',color='Count')

plot_city=Data['thalach'].value_counts()[0:50].reset_index()
plot_city.columns=['thalach','Count']
px.bar(plot_city,x='thalach',y='Count',template='gridon',
      title='thalach',color='Count')

plot_city=Data['exang'].value_counts()[0:50].reset_index()
plot_city.columns=['exang','Count']
px.bar(plot_city,x='exang',y='Count',template='gridon',
      title='exang',color='Count')

import plotly.express as px

plot_city=Data['oldpeak'].value_counts()[0:50].reset_index()
plot_city.columns=['oldpeak','Count']
px.bar(plot_city,x='oldpeak',y='Count',template='gridon',
      title='oldpeak',color='Count')

plot_city=Data['slope'].value_counts()[0:50].reset_index()
plot_city.columns=['slope','Count']
px.bar(plot_city,x='slope',y='Count',template='gridon',
      title='slope',color='Count')

plot_city=Data['ca'].value_counts()[0:50].reset_index()
plot_city.columns=['ca','Count']
px.bar(plot_city,x='ca',y='Count',template='gridon',
      title='ca',color='Count')

plot_city=Data['thal'].value_counts()[0:50].reset_index()
plot_city.columns=['thal','Count']
px.bar(plot_city,x='thal',y='Count',template='gridon',
      title='thal',color='Count')

plot_city=Data['target'].value_counts()[0:50].reset_index()
plot_city.columns=['target','Count']
px.bar(plot_city,x='target',y='Count',template='gridon',
      title='target',color='Count')

Data.hist(figsize = (12, 12))
plt.show()

sns.barplot(x='age',y='target',data=Data)
plt.xticks(rotation=90)
plt.show()

sns.barplot(x='age',y='trestbps',data=Data)
plt.xticks(rotation=90)
plt.show()

sns.barplot(x='thal',data=Data)
plt.xticks(rotation=90)
plt.show()

fig=plt.gcf()
fig.set_size_inches(10, 6)
sns.boxplot(x='age',y='target',data=Data)
plt.xticks(rotation=90)
plt.show()

fig=plt.gcf()
fig.set_size_inches(10, 6)
sns.boxplot(x='age',data=Data)
plt.xticks(rotation=90)
plt.show()

fig=plt.gcf()
fig.set_size_inches(10, 6)
sns.boxplot(x='sex',data=Data)
plt.xticks(rotation=90)
plt.show()

fig=plt.gcf()
fig.set_size_inches(10, 6)
sns.boxplot(x='cp',data=Data)
plt.xticks(rotation=90)
plt.show()

fig=plt.gcf()
fig.set_size_inches(10, 6)
sns.boxplot(x='trestbps',data=Data)
plt.xticks(rotation=90)
plt.show()

fig=plt.gcf()
fig.set_size_inches(10, 6)
sns.boxplot(x='chol',data=Data)
plt.xticks(rotation=90)
plt.show()

fig=plt.gcf()
fig.set_size_inches(10, 6)
sns.boxplot(x='fbs',data=Data)
plt.xticks(rotation=90)
plt.show()

fig=plt.gcf()
fig.set_size_inches(10, 6)
sns.boxplot(x='restecg',data=Data)
plt.xticks(rotation=90)
plt.show()

fig=plt.gcf()
fig.set_size_inches(10, 6)
sns.boxplot(x='thalach',data=Data)
plt.xticks(rotation=90)
plt.show()

fig=plt.gcf()
fig.set_size_inches(10, 6)
sns.boxplot(x='exang',data=Data)
plt.xticks(rotation=90)
plt.show()

fig=plt.gcf()
fig.set_size_inches(10, 6)
sns.boxplot(x='oldpeak',data=Data)
plt.xticks(rotation=90)
plt.show()

fig=plt.gcf()
fig.set_size_inches(10, 6)
sns.boxplot(x='slope',data=Data)
plt.xticks(rotation=90)
plt.show()

fig=plt.gcf()
fig.set_size_inches(10, 6)
sns.boxplot(x='ca',data=Data)
plt.xticks(rotation=90)
plt.show()

fig=plt.gcf()
fig.set_size_inches(10, 6)
sns.boxplot(x='thal',data=Data)
plt.xticks(rotation=90)
plt.show()

fig=plt.gcf()
fig.set_size_inches(10, 6)
sns.boxplot(x='target',data=Data)
plt.xticks(rotation=90)
plt.show()

sns.kdeplot(data=Data, x='sex', bw_method=.15)

<Axes: xlabel='sex', ylabel='Density'>

sns.kdeplot(data=Data, x='age', bw_method=.15)

<Axes: xlabel='age', ylabel='Density'>

sns.kdeplot(data=Data, x='cp', bw_method=.15)

<Axes: xlabel='cp', ylabel='Density'>

sns.kdeplot(data=Data, x='trestbps', bw_method=.15)

<Axes: xlabel='trestbps', ylabel='Density'>

sns.kdeplot(data=Data, x='chol', bw_method=.15)

<Axes: xlabel='chol', ylabel='Density'>

sns.kdeplot(data=Data, x='fbs', bw_method=.15)

<Axes: xlabel='fbs', ylabel='Density'>

sns.kdeplot(data=Data, x='restecg', bw_method=.15)

<Axes: xlabel='restecg', ylabel='Density'>

sns.kdeplot(data=Data, x='thalach', bw_method=.15)

<Axes: xlabel='thalach', ylabel='Density'>

sns.kdeplot(data=Data, x='exang', bw_method=.15)

<Axes: xlabel='exang', ylabel='Density'>

sns.kdeplot(data=Data, x='oldpeak', bw_method=.15)

<Axes: xlabel='oldpeak', ylabel='Density'>

sns.kdeplot(data=Data, x='slope', bw_method=.15)

<Axes: xlabel='slope', ylabel='Density'>

sns.kdeplot(data=Data, x='ca', bw_method=.15)

<Axes: xlabel='ca', ylabel='Density'>

sns.kdeplot(data=Data, x='thal', bw_method=.15)

<Axes: xlabel='thal', ylabel='Density'>

sns.kdeplot(data=Data, x='target', bw_method=.15)

<Axes: xlabel='target', ylabel='Density'>

sns.kdeplot(data=Data, x='age', bw_method=.15, hue='sex')

<Axes: xlabel='age', ylabel='Density'>

sns.kdeplot(data=Data, x='thal', bw_method=.15, hue='target')

<Axes: xlabel='thal', ylabel='Density'>

sns.distplot(Data.age)

<Axes: xlabel='age', ylabel='Density'>

sns.distplot(Data.sex)

<Axes: xlabel='sex', ylabel='Density'>

age 0 gendar 0 chest_pain 0 trestbps 0 chol 0 fbs 0 restecg 0 thalach 0 exang 0 oldpeak 0 slope 0 ca 0 thal 0 target

sns.distplot(Data.cp)

<Axes: xlabel='cp', ylabel='Density'>

sns.distplot(Data.trestbps)

<Axes: xlabel='trestbps', ylabel='Density'>

sns.distplot(Data.chol)

<Axes: xlabel='chol', ylabel='Density'>

sns.distplot(Data.fbs)

<Axes: xlabel='fbs', ylabel='Density'>

sns.distplot(Data.restecg)

<Axes: xlabel='restecg', ylabel='Density'>

sns.distplot(Data.thalach)

<Axes: xlabel='thalach', ylabel='Density'>

sns.distplot(Data.exang)

<Axes: xlabel='exang', ylabel='Density'>

sns.distplot(Data.oldpeak)

<Axes: xlabel='oldpeak', ylabel='Density'>

sns.distplot(Data.slope)

<Axes: xlabel='slope', ylabel='Density'>

sns.distplot(Data.ca)

<Axes: xlabel='ca', ylabel='Density'>

sns.distplot(Data.thal)

<Axes: xlabel='thal', ylabel='Density'>

sns.distplot(Data.target)

<Axes: xlabel='target', ylabel='Density'>

sns.set_theme()
sns.set_palette(sns.color_palette('rocket', 3))
sns.displot(Data, x='age', hue='target', bins=30, linewidth=0, height=5, kde=True, aspect=1.6)
plt.show()

sns.set_theme()
sns.set_palette(sns.color_palette('rocket', 3))
sns.displot(Data, x='sex', hue='target', bins=30, linewidth=0, height=5, kde=True, aspect=1.6)
plt.show()

sns.set_theme()
sns.set_palette(sns.color_palette('rocket', 3))
sns.displot(Data, x='cp', hue='target', bins=30, linewidth=0, height=5, kde=True, aspect=1.6)
plt.show()

sns.set_theme()
sns.set_palette(sns.color_palette('rocket', 3))
sns.displot(Data, x='trestbps', hue='target', bins=30, linewidth=0, height=5, kde=True, aspect=1.6)
plt.show()

sns.set_theme()
sns.set_palette(sns.color_palette('rocket', 3))
sns.displot(Data, x='chol', hue='target', bins=30, linewidth=0, height=5, kde=True, aspect=1.6)
plt.show()

sns.set_theme()
sns.set_palette(sns.color_palette('rocket', 3))
sns.displot(Data, x='fbs', hue='target', bins=30, linewidth=0, height=5, kde=True, aspect=1.6)
plt.show()

sns.set_theme()
sns.set_palette(sns.color_palette('rocket', 3))
sns.displot(Data, x='restecg', hue='target', bins=30, linewidth=0, height=5, kde=True, aspect=1.6)
plt.show()

sns.set_theme()
sns.set_palette(sns.color_palette('rocket', 3))
sns.displot(Data, x='thalach', hue='target', bins=30, linewidth=0, height=5, kde=True, aspect=1.6)
plt.show()

sns.set_theme()
sns.set_palette(sns.color_palette('rocket', 3))
sns.displot(Data, x='exang', hue='target', bins=30, linewidth=0, height=5, kde=True, aspect=1.6)
plt.show()

sns.set_theme()
sns.set_palette(sns.color_palette('rocket', 3))
sns.displot(Data, x='oldpeak', hue='target', bins=30, linewidth=0, height=5, kde=True, aspect=1.6)
plt.show()

sns.set_theme()
sns.set_palette(sns.color_palette('rocket', 3))
sns.displot(Data, x='slope', hue='target', bins=30, linewidth=0, height=5, kde=True, aspect=1.6)
plt.show()

sns.set_theme()
sns.set_palette(sns.color_palette('rocket', 3))
sns.displot(Data, x='ca', hue='target', bins=30, linewidth=0, height=5, kde=True, aspect=1.6)
plt.show()

sns.set_theme()
sns.set_palette(sns.color_palette('rocket', 3))
sns.displot(Data, x='thal', hue='target', bins=30, linewidth=0, height=5, kde=True, aspect=1.6)
plt.show()

DecisionTreeRegressor

from sklearn.preprocessing import LabelEncoder

for i in col:
    Data[i] = le.fit_transform(Data[i].astype(str))

Data.head()

	age	sex	cp	trestbps	chol	fbs	restecg	thalach	exang	oldpeak	slope	ca	thal	target
0	63	1	3	145	233	1	0	150	0	2	0	0	1	1
1	37	1	2	130	250	0	1	187	0	3	0	0	2	1
2	41	0	1	130	204	0	0	172	0	1	2	0	2	1
3	56	1	1	120	236	0	1	178	0	0	2	0	2	1
4	57	0	0	120	354	0	1	163	1	0	2	0	2	1

x= Data.iloc[:,0:-1]
y= Data.iloc[:,-1]

from sklearn.model_selection import train_test_split

Xtrain, Xtest, ytrain, ytest = train_test_split(x, y, test_size=0.2, random_state=1)

print("Training samples:", Xtrain.shape)
print("Testing samples:", Xtest.shape)

Training samples: (241, 13)
Testing samples: (61, 13)

from sklearn.tree import DecisionTreeClassifier
clf = DecisionTreeClassifier()
clf =clf.fit(Xtrain, ytrain)
y_pred = clf.predict(Xtest)

from sklearn import metrics
print("Accuracy:{0}%".format(metrics.accuracy_score(ytest,y_pred)*100))

Accuracy:77.04918032786885%

from sklearn.metrics import confusion_matrix
import seaborn as sns
import numpy as np
cm = confusion_matrix(ytest, y_pred)

print(cm)
sns.heatmap(cm/np.sum(cm), annot=True,fmt='.2%',cmap='Blues')

[[21  8]
 [ 6 26]]

<Axes: >

from sklearn.metrics import classification_report
print(classification_report(ytest, y_pred))

              precision    recall  f1-score   support

           0       0.78      0.72      0.75        29
           1       0.76      0.81      0.79        32

    accuracy                           0.77        61
   macro avg       0.77      0.77      0.77        61
weighted avg       0.77      0.77      0.77        61

from sklearn.tree import DecisionTreeRegressor
DtReg = DecisionTreeRegressor()

DtReg.fit(Xtrain, ytrain)
row = [2, 4, 6, 7, 10, 30, 12, 32, 23, 15, 21, 20, 31]
DtReg_yhat = DtReg.predict([row])

print(DtReg_yhat[0])

0.0